[
  {
    "Accuracy": 0.35,
    "code_links": [],
    "date": "2020-03-06",
    "date2": 20200306,
    "model": "SSML",
    "paper": {
      "title": "Noise Estimation Using Density Estimation for Self-Supervised Multimodal Learning",
      "url": "https://cknow.io/lib/baa0fae2f5d59446"
    },
    "paper_data_uoa": "baa0fae2f5d59446"
  },
  {
    "Accuracy": 0.33,
    "code_links": [
      {
        "title": "fanchenyou/HME-VideoQA",
        "url": "https://github.com/fanchenyou/HME-VideoQA"
      }
    ],
    "date": "2019-04-08",
    "date2": 20190408,
    "model": "HMEMA",
    "paper": {
      "title": "Heterogeneous Memory Enhanced Multimodal Attention Model for Video Question Answering",
      "url": "https://cknow.io/lib/b64d34549411f9de"
    },
    "paper_data_uoa": "b64d34549411f9de"
  },
  {
    "Accuracy": 0.32,
    "code_links": [],
    "date": "2018-03-29",
    "date2": 20180329,
    "model": "Co-Mem",
    "paper": {
      "title": "Motion-Appearance Co-Memory Networks for Video Question Answering",
      "url": "https://cknow.io/lib/7013e60944c48941"
    },
    "paper_data_uoa": "7013e60944c48941"
  },
  {
    "Accuracy": 0.309,
    "code_links": [],
    "date": "2017-04-14",
    "date2": 20170414,
    "model": "ST-VQA",
    "paper": {
      "title": "TGIF-QA: Toward Spatio-Temporal Reasoning in Visual Question Answering",
      "url": "https://cknow.io/lib/cb9107eee4a98b5a"
    },
    "paper_data_uoa": "cb9107eee4a98b5a"
  }
]